Subject: Re: [AUDITORY] Related Work on Sound Polyphony Estimation From: Adam Weisser <adam_weisser@xxxxxxxx> Date: Thu, 15 Sep 2022 00:26:10 +0700--584c8fb354cc411fbfc8cd4989f671f6 Content-Type: text/plain;charset=utf-8 Content-Transfer-Encoding: quoted-printable Dear Jakob, We tested the number of sound objects that listeners recognized in sever= al everyday environments (2 minutes long each) from the ARTE database. I= 'm not aware of other published tests with realistic sound environments,= but only some that tested the "numerosity" perception using various syn= thesized complex stimuli. These (up to 2018) were all cited in the same = work (Chapter 5 of my dissertation): https://www.researchonline.mq.edu.au/vital/access/services/Download/mq:7= 0667/SOURCE1 All the best, Adam.=20 On Tue, Sep 13, 2022, at 7:16 PM, Abe=C3=9Fer, Jakob wrote: > Dear list, > =20 > we=E2=80=99re currently conducting a literature review on methods for = the task of sound polyphony estimation, i.e., counting the number of sou= nd events in a short audio segment. > While there exists several works on related =E2=80=9Ccounting=E2=80=9D= tasks such as speaker counting, music instrument counting, ensemble siz= e estimation, and note polyphony estimation, > we were not able to find many references with focus on everyday / envi= ronmental sounds. > If you are aware of relevant literature, I would very much appreciate = any pointers. > =20 > Thank you & best regards > Jakob Abe=C3=9Fer > =20 > -- > Dr.-Ing. Jakob Abe=C3=9Fer > Senior Scientist > Semantic Music Technologies >=20 > Fraunhofer Institute for Digital Media Technology IDMT > Ehrenbergstr. 31 > 98693 Ilmenau, Germany >=20 > Phone +49 3677 467-288 > Fax +49 3677 467-467 >=20 > Email: jakob.abesser@xxxxxxxx > http://www.idmt.fraunhofer.de > =20 --584c8fb354cc411fbfc8cd4989f671f6 Content-Type: text/html;charset=utf-8 Content-Transfer-Encoding: quoted-printable <!DOCTYPE html><html><head><title></title><style type=3D"text/css">#qt p= .qt-MsoNormal{margin-top:0cm;margin-right:0cm;margin-bottom:0cm;margin-l= eft:0cm;font-size:11pt;font-family:"Calibri", sans-serif;} p.MsoNormal,p.MsoNoSpacing{margin:0}</style></head><body><div style=3D"f= ont-family:Arial;">Dear Jakob,<br></div><div style=3D"font-family:Arial;= "><br></div><div style=3D"font-family:Arial;">We tested the number of so= und objects that listeners recognized in several everyday environments (= 2 minutes long each) from the ARTE database. I'm not aware of other publ= ished tests with realistic sound environments, but only some that tested= the "numerosity" perception using various synthesized complex stimuli. = These (up to 2018) were all cited in the same work (Chapter 5 of my diss= ertation):<br></div><div style=3D"font-family:Arial;"><br></div><div sty= le=3D"font-family:Arial;"><a href=3D"https://www.researchonline.mq.edu.a= u/vital/access/services/Download/mq:70667/SOURCE1">https://www.researcho= nline.mq.edu.au/vital/access/services/Download/mq:70667/SOURCE1</a><br><= /div><div style=3D"font-family:Arial;"><br></div><div style=3D"font-fami= ly:Arial;">All the best,<br></div><div style=3D"font-family:Arial;">Adam= . <br></div><div style=3D"font-family:Arial;"><br></div><div>On Tue, Sep= 13, 2022, at 7:16 PM, Abe=C3=9Fer, Jakob wrote:<br></div><blockquote ty= pe=3D"cite" id=3D"qt" style=3D"overflow-wrap:break-word;"><div class=3D"= qt-WordSection1"><p class=3D"qt-MsoNormal">Dear list,<br></p><p class=3D= "qt-MsoNormal"> <br></p><p class=3D"qt-MsoNormal"><span lang=3D"EN-= US">we=E2=80=99re currently conducting a literature review on methods fo= r the task of sound polyphony estimation, i.e., counting the number of s= ound events in a short audio segment.</span><br></p><p class=3D"qt-MsoNo= rmal"><span lang=3D"EN-US">While there exists several works on related =E2= =80=9Ccounting=E2=80=9D tasks such as speaker counting, music instrument= counting, ensemble size estimation, and note polyphony estimation,</spa= n><br></p><p class=3D"qt-MsoNormal"><span lang=3D"EN-US">we were not abl= e to find many references with focus on everyday / environmental sounds.= </span><br></p><p class=3D"qt-MsoNormal"><span lang=3D"EN-US">If you are= aware of relevant literature, I would very much appreciate any pointers= .</span><br></p><p class=3D"qt-MsoNormal"><span lang=3D"EN-US"> </s= pan><br></p><p class=3D"qt-MsoNormal"><span lang=3D"EN-US">Thank you &am= p; best regards</span><br></p><p class=3D"qt-MsoNormal"><span lang=3D"EN= -US">Jakob Abe=C3=9Fer</span><br></p><p class=3D"qt-MsoNormal"><span lan= g=3D"EN-US"> </span><br></p><p class=3D"qt-MsoNormal"><span style=3D= "">--</span><br></p><p class=3D"qt-MsoNormal"><span style=3D"">Dr.-Ing. = Jakob Abe=C3=9Fer</span><br></p><p class=3D"qt-MsoNormal"><span style=3D= "">Senior Scientist<br> Semantic Music Technologies<br> <br> Fraunhofer = Institute for Digital Media Technology IDMT<br> Ehrenbergstr. 31<br> 986= 93 Ilmenau, Germany<br> <br> Phone +49 3677 467-288<br> Fax +49 3677 467= -467<br> <br> Email: jakob.abesser@xxxxxxxx<br> http://www.idm= t.fraunhofer.de</span></p><p class=3D"qt-MsoNormal"> <br></p></div>= </blockquote><div style=3D"font-family:Arial;"><br></div></body></html> --584c8fb354cc411fbfc8cd4989f671f6--